ViperEkura 5c180cfa90 fix : handle zero-token batch generation ...

- return empty results without running inference for non-positive limits
- keep scheduler batch outputs aligned with requested max_tokens
- add engine and scheduler regression coverage

2026-08-06 12:31:09 +08:00

..

conftest.py

refactor : FastAPI 懒加载单例，消除模块级副作用

2026-06-04 15:52:27 +08:00

test_cache.py

feat : add radix prefix cache

2026-08-06 11:45:52 +08:00

test_engine.py

fix : handle zero-token batch generation

2026-08-06 12:31:09 +08:00

test_protocol.py

feat : BaseToolParser.feed 增加可选 token_ids 参数

2026-06-06 11:19:30 +08:00

test_sample.py

refactor: unify rollout onto inference engine KV-cache path

2026-07-20 12:52:20 +08:00

test_scheduler.py

fix : handle zero-token batch generation

2026-08-06 12:31:09 +08:00

test_server.py

refactor : FastAPI 懒加载单例，消除模块级副作用

2026-06-04 15:52:27 +08:00

test_task.py

fix : correct prefill sampling and record alignment

2026-08-05 22:20:29 +08:00

test_tool_parser.py

test: prune low-value and duplicate tests

2026-08-01 16:01:20 +08:00